I got tired of doing this and set up a /question skill that forbids the agent from doing anything that would modify my files. It makes it very clear what the intent of every prompt is.

Similarly, I have an /info skill that tells the agent to read my prompt, update any memories it thinks it should, then pass the turn.

This is clever and I can't believe I didn't think of it. I'm so used to appending "don't make any changes" to the end of my prompts.

>Similarly, I have an /info skill that tells the agent to read my prompt, update any memories it thinks it should, then pass the turn.

Could you give me a quick example? I think I’m not getting it, but it sounds interesting.

Very simple but clever solution. I’ll probably do something like this as well

balk is the American spelling of baulk, meaning to hesitate, stop short, or refuse to proceed due to reluctance, fear, or an obstacle.

"He got personal visits from both Ballmer and Gates that pressured him to stay with Microsoft but did not balk" can be rephrased as "He was pressured by Microsoft [to stay with Windows] but that pressure did not cause him to hesitate [with switching to Linux]."

If he did not balk that means he did not refuse. Which means he complied.

What he did not do was comply/capitulate/etc.

Merriam-Webster has balk as to stop short and refuse to proceed. To understand the intended meaning, put the emphasis on the first part: If the mayor did not balk, he did not stop, that is, he refused to comply and proceeded with his plan.

> Merriam-Webster has balk as to stop short and refuse to proceed. To understand the intended meaning, put the emphasis on the first part: If the mayor did not balk, he did not stop, that is, he refused to comply and proceeded with his plan.

I feel like one of us is extremely confused.

"Balk" = "stop" = "refuse to proceed", right?

So "<did not> balk" = "<did not> stop" = "<did not> refuse to proceed", right?

"<Did not> refuse to proceed" with Microsoft's proposal therefore means he in fact complied with Microsoft's proposal and did proceed with it, right?

The thing he "<Did not> refuse to proceed" with was LiMux, his project for moving away from Microsoft.

From your site, under "How we find each photo's real date" section:

Sequence Neighboring photos

Photos scanned in alphabetical order often belong together, so nearby files can give useful context to each other.

For humans, yes. For software, not so much.

There’s a special rule in SemVer that states when the leading major version is 0, every minor version bump is considered breaking.

https://semver.org/#spec-item-4

NPM handles 0.x.y versions of packages differently from 1+.x.y

https://github.com/npm/node-semver#caret-ranges-123-025-004

Several major packages are still on 0.x.y and (ab)use this feature when updating without "committing" to a major version.

Thanks for the explanation, crucial to explain why.

Many modern podcasts don't actually include any ads in their source audio, relying instead on dynamic ad insertion.

Many podcast hosts provide dynamic ad insertion functionality. Unlike baked-in ads, podcast creators mark the locations of where ads can be inserted and, when requested by a user, the host generates a new MP3 on-the-fly using the user's tracking data (geolocation, demographics, etc.) that is then downloaded to their device.

This allows old podcasts to continue to generate ad revenue by dynamically inserting ads from currently-running ad campaigns.

https://advertise.acast.com/news-and-insights/the-benefits-o...

This really addresses my question directly. Thank you. It makes a lot of sense.

I wonder if this ad insertion happens for downloading directly from RSS feeds as well. Typically, there is a link in the RSS feed directly to an .mp3 file, and I don't know if it would be possible to set the RSS link to a URL which would custom "build" a new mp3 for each download with dynamic ads injected. Is it just the case that some podcasts do not have "public" RSS feeds? I don't know if i've come across any...

If downloaded from the podcast host, it'll always insert ads.

To answer your original question, I threw together a python script that takes an RSS feed and downloads all the podcasts in that feed.

https://gist.github.com/zachwlewis/7ad4182e21768dae98cabd17b...

Hope that helps!

Fantastic. I appreciate it very much!